Segmentation of low scattering region in SAR images using multi-module fusion network. Issue 14 (18th July 2022)

• Record Type: Journal Article
• Authors: Yang, Xiaqing; Zhou, Yuanyuan; Chen, Tingjun; Shi, Jun; Cui, Guolong
• Is Part Of: International journal of remote sensing. Volume 43:Issue 14(2022)
• Page Start: 5439
• Page End: 5451
• Publication Date: 2022-07-18
• Subjects: Synthetic aperture radar (SAR) -- low scattering region -- convolutional neural network (CNN); Remote sensing -- Periodicals; Télédétection -- Périodiques; 621.3678
• DOI: 10.1080/01431161.2022.2135411
• Languages: English
• ISSNs: 0143-1161

Abstract

ABSTRACT: The proposed multi-module fusion network (MMFNet) is designed for the segmentation of low scattering regions such as roads, waters, and shadows in synthetic aperture radar (SAR) images in this paper. It is primarily comprised of three modules, i.e. high-resolution backbone network module, spatial pyramid pooling convolution (SPPC) module, and channel attention module, and trained with weighted cross-entropy loss. The high-resolution backbone network works to retain high resolution of feature maps and reduce spatial accuracy loss, which contributes to the extraction of edge information. SPPC module performs multi-scale feature fusion, extracts target areas with different sizes and improves network accuracy. Channel attention module intensifies network expression of category information, thus further improves network performance. Our experimental analysis using real SAR data shows that MMFNet achieves good low scattering region segmentation, with mean IoU (MIoU) reaching up to 82.5 % .